Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add CrestApps/CrestApps.AgentSkills --skill crestapps-core-templatesgit clone --depth 1 https://github.com/CrestApps/CrestApps.AgentSkillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/crestapps/crestapps.agentskills/crestapps-core-templates)<a href="https://agentmods.dev/skills/crestapps/crestapps.agentskills/crestapps-core-templates"><img src="https://agentmods.dev/badge/skills/crestapps/crestapps.agentskills/crestapps-core-templates/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/crestapps/crestapps.agentskills/crestapps-core-templates"><img src="https://agentmods.dev/badge/skills/crestapps/crestapps.agentskills/crestapps-core-templates.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00170 | $0.01813 |
| Opus 5.5 | $0.00068 | $0.00725 |
| Sonnet 5.5 | $0.00034 | $0.00363 |
| Haiku 4.5 | $0.00017 | $0.00181 |
Grade A, and why
crestapps-core-templates scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CrestApps.Core Templates
You are a CrestApps.Core expert. Generate code for CrestApps.Core.Templates discovery, Liquid rendering and composition.
Guidelines
CrestApps.Core.Templatesis standalone.services.AddTemplating(...)registersITemplateEngine(FluidTemplateEngine, singleton),ITemplateService(DefaultTemplateService, scoped), the MarkdownITemplateParser, and the code, file-system and prompt file-system providers. It also adds theinclude_promptLiquid filter.CrestApps.Core.AIalready callsAddTemplating()throughAddCoreAITemplating(), which adds AI template sources and the system-prompt profile template provider. Usecrestapps-core-ai-templatesfor that layer.ITemplateService.RenderAsync(id, arguments)renders a registered template;ITemplateEngine.RenderAsync(text, arguments)renders an in-memory Liquid string.FluidTemplateEngineuses Fluid's deny-by-default member access. Register every POCO a template reads:services.Configure<Fluid.TemplateOptions>(o => o.MemberAccessStrategy.Register<Customer>()). Dictionaries and primitives need no registration.- Rendering trims each line and collapses runs of blank lines. A template that fails to parse is logged as a warning and returned unrendered; check templates with
TryValidatebefore saving them. - Template identifiers are case-insensitive. When two providers return the same
Id, the first one read wins. ITemplateService,ITemplateEngineandITemplateProvidermembers take an optionalCancellationToken; pass it through custom providers.
Registration
using CrestApps.Core.Templates.Extensions;
builder.Services
.AddTemplating(options => options
.AddDiscoveryPath(builder.Environment.ContentRootPath)
.AddTemplate(
"welcome",
"Hello {{ customer }}!",
metadata => metadata.Title = "Welcome"))
.AddTemplatesFromAssembly(typeof(Program).Assembly, source: "MyApp");
| Source | Template id | Kind |
|---|---|---|
AddTemplate(id, content, ...) |
the given id | set Template.Kind yourself |
{discovery path}/Templates/*.md (not recursive) |
file name without extension | from Kind front matter |
{discovery path}/Templates/Prompts/*.md and one level of subfolders |
file name; a subfolder name becomes FeatureId |
SystemPrompt unless front matter sets it |
Embedded resources under Templates/ via AddTemplatesFromAssembly(...) |
path after Templates.; a Prompts. prefix is dropped |
SystemPrompt for Prompts/, otherwise front matter |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday Changed · +74 lines · +148 tokens per session 833749840f41
- 1mo ago First seen · 88 lines · 22 tokens per session scan A bb7d34c85f5c
crestapps-core-templates is a skill published in the GitHub repository CrestApps/CrestApps.AgentSkills (13 stars, last pushed yesterday), licensed MIT. It adds 170 tokens to every session and 1,813 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
tech-specs
To define clear, testable tech specs from requirements — target-state architecture, contracts, interfaces.
sast-idor
Detect Insecure Direct Object Reference (IDOR) vulnerabilities in a codebase using a three-phase approach: recon (find candidates), batched verify (check authorization in parallel subagents, 3 candidates each), and merge (consolidate batch results). Checks endpoints for missing ownership or authorization checks on…
api-mirror
Stand up a persistent, self-refreshing local mirror of a bulk upstream dataset with the MirrorService (@cyanheads/mcp-ts-core/mirror). Use when a server wraps a large or slow API and should query a synced local index (embedded SQLite + FTS5) instead of paginating the live API per request.
add-service
Scaffold a new service integration. Use when the user asks to add a service, integrate an external API, or create a reusable domain module with its own initialization and state.
api-utils
API reference for all utilities exported from @cyanheads/mcp-ts-core/utils. Use when looking up utility method signatures, options, peer dependencies, or usage patterns.
api-workers
Cloudflare Workers deployment using createWorkerHandler from @cyanheads/mcp-ts-core/worker. Covers the full handler signature, binding types, CloudflareBindings extensibility, runtime compatibility guards, and wrangler.toml requirements.